NCR has filed a patent for a method that uses historical transaction data and real-time data to predict when a transaction terminal will require a media intervention. The method involves preprocessing the data, training a machine-learning model, and providing the predicted elapsed times through an interface. GlobalData’s report on NCR gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
Access deeper industry intelligence
Experience unmatched clarity with a single platform that combines unique data, AI, and human expertise.
According to GlobalData’s company profile on NCR, Automated Teller Machines (ATM) was a key innovation area identified from patents. NCR's grant share as of September 2023 was 75%. Grant share is based on the ratio of number of grants to total number of patents.
Predicting replenishment activities for transaction terminals using machine learning
A recently filed patent (Publication Number: US20230316271A1) describes a method for predicting when transaction terminals will require media intervention. The method involves receiving real-time data associated with transactions and media events at transaction terminals. From this data, transaction patterns and media usage patterns are calculated for each terminal. The real-time data is then modified with these patterns and passed as input to a machine-learning model (MLM). The MLM outputs a transaction terminal identifier for each terminal, along with a predicted elapsed time until the terminal is expected to require a media intervention. This information is provided through an interface.
The method can be iterated at configured intervals of time, allowing for continuous monitoring and prediction of media intervention requirements. Additionally, the method can be processed as a Software-as-a-Service (SaaS), providing a convenient and scalable solution.
The calculation of transaction patterns involves determining the total number of transactions processed on each terminal during a given interval of time, divided by the total number of transactions processed by all terminals during the same interval. Similarly, media usage patterns are calculated by dividing the cash payment total number of transactions for each terminal by the corresponding total number of transactions.
The modified real-time data includes labels for transaction patterns, media usage patterns, and each field of the original data. This modified data is then passed as input to the MLM.
The predicted elapsed times and transaction terminal identifiers are provided through an interface, which can update a dashboard view or be accessed through a browser interface or a user interface associated with a mobile application.
Another method described in the patent involves obtaining historical data for a store, including transaction data, transaction terminal statuses, and media metrics and events. The historical data is filtered based on specific transaction terminal statuses, and then preprocessed by adding transaction patterns, media usage patterns, and elapsed times before encountering the specific terminal status. A machine-learning model is derived during a training session using this preprocessed data, and then applied to real-time data to provide predicted elapsed times for media interventions.
The system described in the patent includes a cloud server with a processor and a computer-readable storage medium. The processor executes instructions to perform the various operations of the method, including obtaining historical and real-time data, preprocessing the data, training the MLM, and providing the predicted elapsed times and transaction terminal identifiers through an interface.
Overall, this patent presents a method and system for predicting when transaction terminals will require media intervention, allowing for efficient management and allocation of resources.
To know more about GlobalData’s detailed insights on NCR, buy the report here.
Data Insights
From
The gold standard of business intelligence.
Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.
GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.
GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.
